© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 17507
    Prev
    Next
    INDEX
    Explanations

    terms related to specific sports teams and news

    oai_token-act-pair · gpt-3.5-turbo

    topics related to sports and news coverage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disbanded
    -0.78
    ledged
    -0.76
    wark
    -0.74
    owicz
    -0.69
    pex
    -0.68
    aterasu
    -0.66
    orically
    -0.66
    aft
    -0.65
    rers
    -0.64
    lication
    -0.63
    POSITIVE LOGITS
     news
    1.37
     NEWS
    1.20
     News
    1.14
    news
    1.12
     newsletter
    1.08
     podcasts
    1.04
     âĢº
    1.04
     commentary
    1.02
     stories
    1.01
     headlines
    1.00
    Activations Density 0.222%

    No Known Activations